Fair Face Verification by Using Non-Sensitive Soft-Biometric Attributes

Simple item page
dc.contributor.authorVillalobos, Esteban
dc.contributor.authorMery, Domingo
dc.contributor.authorBowyer, Kevin
dc.date.accessioned2025-01-20T21:11:07Z
dc.date.available2025-01-20T21:11:07Z
dc.date.issued2022
dc.description.abstractFacial recognition has been shown to have different accuracy for different demographic groups. When setting a threshold to achieve a specific False Match Rate (FMR) on a mixed demographic impostor distribution, some demographic groups can experience a significantly worse FMR. To mitigate this, some authors have proposed to use demographic-specific thresholds. However, this can be impractical in an operational scenario, as it would either require users to report their demographic group or the system to predict the demographic group of each user. Both of these options can be deemed controversial since the demographic group is a sensitive attribute. Further, this approach requires listing the possible demographic groups, which can become controversial in itself. We show that a similar mitigation effect can be achieved using non-sensitive predicted soft-biometric attributes. These attributes are based on the appearance of the users (such as hairstyle, accessories, and facial geometry) rather than how the users self-identify. Our experiments use a set of 38 binary non-sensitive attributes from the MAAD-Face dataset. We report results on the Balanced Faces in the Wild dataset, which has a balanced number of identities by race and gender. We compare clustering-based and decision-tree-based strategies for selecting thresholds. We show that the proposed strategies can reduce differential outcomes in intersectional groups twice as effectively as using gender-specific thresholds and, in some cases, are also better than using race-specific thresholds.
dc.description.funderFondecyt from CONICYT-Chile
dc.fuente.origenWOS
dc.identifier.doi10.1109/ACCESS.2022.3158967
dc.identifier.issn2169-3536
dc.identifier.urihttps://doi.org/10.1109/ACCESS.2022.3158967
dc.identifier.urihttps://repositorio.uc.cl/handle/11534/93610
dc.identifier.wosidWOS:000772393100001
dc.language.isoen
dc.pagina.final30179
dc.pagina.inicio30168
dc.revistaIeee access
dc.rightsacceso restringido
dc.subjectFace recognition
dc.subjectTraining
dc.subjectLicenses
dc.subjectGraphics
dc.subjectError analysis
dc.subjectDecision trees
dc.subjectNIST
dc.subjectFacial recognition
dc.subjectfairness
dc.subjectdifferential outcomes
dc.subjectsoft-biometric attributes
dc.titleFair Face Verification by Using Non-Sensitive Soft-Biometric Attributes
dc.typeartículo
dc.volumen10
sipa.indexWOS
sipa.trazabilidadWOS;2025-01-12
Files
Collections
Artículos de revistas